Evaluation of prioritized deep system identification on a path following task - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Intelligent & Robotic Systems Année : 2021

Evaluation of prioritized deep system identification on a path following task

Antoine Mahé
Antoine Richard
  • Fonction : Auteur
  • PersonId : 1087046
Matthieu Geist
  • Fonction : Auteur
  • PersonId : 790158
  • IdRef : 142341819
Cedric Pradalier

Résumé

This paper revisits system identification and shows how new paradigms from machine learning can be used to improve it in the case of non-linear systems modeling from noisy and unbalanced dataset. We show that using importance sampling schemes in system identification can provide a significant performance boost in modeling, which is helpful to a predictive controller. The performance of the approach is first evaluated on simulated data of a Unmanned Surface Vehicle (USV). Our approach consistently outperforms baseline approaches on this dataset. Moreover we demonstrate the benefits of this identification methodology in a control setting. We use the model of the Unmanned Surface Vehicle (USV) in a Model Predictive Path Integral (MPPI) controller to perform a track following task. We discuss the influence of the controller parameters and show that the prioritized model outperform standard methods. Finally, we apply the Model Predictive Path Integral (MPPI) on a real system using the know-how developed here.
Fichier principal
Vignette du fichier
Importance_Sampling_for_Deep_System_Identification.pdf (4.17 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03138279 , version 1 (11-02-2021)

Identifiants

Citer

Antoine Mahé, Antoine Richard, Stéphanie Aravecchia, Matthieu Geist, Cedric Pradalier. Evaluation of prioritized deep system identification on a path following task. Journal of Intelligent & Robotic Systems , 2021, ⟨10.1007/s10846-021-01341-1⟩. ⟨hal-03138279⟩
59 Consultations
102 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More